| { |
| "best_metric": 0.9975093399750934, |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/BdSLW60_10_Fold/VideoMAE_Kinetics_fold__7__BdSLW60_SKF/checkpoint-6324", |
| "epoch": 9.099501661129569, |
| "eval_steps": 500, |
| "global_step": 9030, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 10.767923355102539, |
| "learning_rate": 4.9889258028792915e-05, |
| "loss": 8.5481, |
| "step": 903 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 0.950186799501868, |
| "eval_loss": 0.33466511964797974, |
| "eval_runtime": 199.5558, |
| "eval_samples_per_second": 4.024, |
| "eval_steps_per_second": 2.014, |
| "step": 903 |
| }, |
| { |
| "epoch": 1.1000553709856036, |
| "grad_norm": 0.11211242526769638, |
| "learning_rate": 4.44567491079119e-05, |
| "loss": 0.3596, |
| "step": 1807 |
| }, |
| { |
| "epoch": 1.1000553709856036, |
| "eval_accuracy": 0.9850560398505604, |
| "eval_loss": 0.05558690428733826, |
| "eval_runtime": 200.7078, |
| "eval_samples_per_second": 4.001, |
| "eval_steps_per_second": 2.003, |
| "step": 1807 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 0.9380614161491394, |
| "learning_rate": 3.8901193552356345e-05, |
| "loss": 0.0616, |
| "step": 2710 |
| }, |
| { |
| "epoch": 2.1, |
| "eval_accuracy": 0.9912826899128269, |
| "eval_loss": 0.043729331344366074, |
| "eval_runtime": 211.8932, |
| "eval_samples_per_second": 3.79, |
| "eval_steps_per_second": 1.897, |
| "step": 2710 |
| }, |
| { |
| "epoch": 3.1000553709856034, |
| "grad_norm": 0.044262029230594635, |
| "learning_rate": 3.334563799680079e-05, |
| "loss": 0.0487, |
| "step": 3614 |
| }, |
| { |
| "epoch": 3.1000553709856034, |
| "eval_accuracy": 0.9937733499377335, |
| "eval_loss": 0.03196950629353523, |
| "eval_runtime": 187.8473, |
| "eval_samples_per_second": 4.275, |
| "eval_steps_per_second": 2.14, |
| "step": 3614 |
| }, |
| { |
| "epoch": 4.1, |
| "grad_norm": 0.4867474436759949, |
| "learning_rate": 2.7796234772978964e-05, |
| "loss": 0.0439, |
| "step": 4517 |
| }, |
| { |
| "epoch": 4.1, |
| "eval_accuracy": 0.9763387297633873, |
| "eval_loss": 0.1842634081840515, |
| "eval_runtime": 198.7263, |
| "eval_samples_per_second": 4.041, |
| "eval_steps_per_second": 2.023, |
| "step": 4517 |
| }, |
| { |
| "epoch": 5.100055370985603, |
| "grad_norm": 0.006861595902591944, |
| "learning_rate": 2.2234526885689677e-05, |
| "loss": 0.0301, |
| "step": 5421 |
| }, |
| { |
| "epoch": 5.100055370985603, |
| "eval_accuracy": 0.9912826899128269, |
| "eval_loss": 0.03178557753562927, |
| "eval_runtime": 196.596, |
| "eval_samples_per_second": 4.085, |
| "eval_steps_per_second": 2.045, |
| "step": 5421 |
| }, |
| { |
| "epoch": 6.1, |
| "grad_norm": 0.004146910738199949, |
| "learning_rate": 1.667897133013412e-05, |
| "loss": 0.0182, |
| "step": 6324 |
| }, |
| { |
| "epoch": 6.1, |
| "eval_accuracy": 0.9975093399750934, |
| "eval_loss": 0.012872942723333836, |
| "eval_runtime": 208.814, |
| "eval_samples_per_second": 3.846, |
| "eval_steps_per_second": 1.925, |
| "step": 6324 |
| }, |
| { |
| "epoch": 7.100055370985603, |
| "grad_norm": 0.0016800760058686137, |
| "learning_rate": 1.1117263442844839e-05, |
| "loss": 0.0067, |
| "step": 7228 |
| }, |
| { |
| "epoch": 7.100055370985603, |
| "eval_accuracy": 0.9962640099626401, |
| "eval_loss": 0.030484894290566444, |
| "eval_runtime": 219.6807, |
| "eval_samples_per_second": 3.655, |
| "eval_steps_per_second": 1.83, |
| "step": 7228 |
| }, |
| { |
| "epoch": 8.1, |
| "grad_norm": 0.006293433252722025, |
| "learning_rate": 5.561707887289283e-06, |
| "loss": 0.0057, |
| "step": 8131 |
| }, |
| { |
| "epoch": 8.1, |
| "eval_accuracy": 0.9962640099626401, |
| "eval_loss": 0.025703083723783493, |
| "eval_runtime": 196.4659, |
| "eval_samples_per_second": 4.087, |
| "eval_steps_per_second": 2.046, |
| "step": 8131 |
| }, |
| { |
| "epoch": 9.099501661129569, |
| "grad_norm": 0.0016384607879444957, |
| "learning_rate": 3.076165866863542e-08, |
| "loss": 0.0006, |
| "step": 9030 |
| }, |
| { |
| "epoch": 9.099501661129569, |
| "eval_accuracy": 0.9962640099626401, |
| "eval_loss": 0.02475578524172306, |
| "eval_runtime": 196.0819, |
| "eval_samples_per_second": 4.095, |
| "eval_steps_per_second": 2.05, |
| "step": 9030 |
| }, |
| { |
| "epoch": 9.099501661129569, |
| "step": 9030, |
| "total_flos": 9.006226676074414e+19, |
| "train_loss": 0.9123596579463511, |
| "train_runtime": 21643.5311, |
| "train_samples_per_second": 3.338, |
| "train_steps_per_second": 0.417 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9030, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.006226676074414e+19, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
